Imports

from utils import print_time_report, print_results, plot_results

Time report

print_time_report()

	hour	min	sec
algo
KNeighborsClassifier	0	5	11
daal4py_KNeighborsClassifier	0	1	9
KNeighborsClassifier_kd_tree	0	1	16
daal4py_KNeighborsClassifier_kd_tree	0	0	46
KMeans	0	7	32
daal4py_KMeans	0	1	58
total	0	17	55

KNeighborsClassifier - Brute Force

print_results(algo="KNeighborsClassifier", versus_lib="daal4py")

plot_results(algo="KNeighborsClassifier", versus_lib="daal4py", group_by_cols=["algorithm", "n_neighbors", "function"], split_hist_by=["n_jobs"])

KNeighborsClassifier - KD Tree

print_results(algo="KNeighborsClassifier_kd_tree", versus_lib="daal4py")

plot_results(algo="KNeighborsClassifier_kd_tree", versus_lib="daal4py", group_by_cols=["algorithm", "n_neighbors", "function"], split_hist_by=["n_jobs"])

KMeans

from utils import _make_dataset
data = _make_dataset('KMeans', 'daal4py', compare_cols=["n_iter"])

data[data["function"] == "fit"].sort_values(["n_iter_sklearn", "n_iter_daal4py"])

	estimator	lib	function	n_samples	n_features	init	max_iter	n_clusters	n_init	tol	adjusted_rand_score	mean_sklearn	stdev_sklearn	n_iter_sklearn	mean_daal4py	stdev_daal4py	n_iter_daal4py	speedup	stdev_speedup
18	KMeans	sklearn	fit	10000	100	k-means++	30	3	1	0.0	NaN	0.4371	0.2018	24.0	0.1011	0.0142	30.0	4.32	14.21
0	KMeans	sklearn	fit	10000	2	k-means++	30	3	1	0.0	NaN	0.0862	0.0478	30.0	0.0126	0.0236	30.0	6.84	2.03
9	KMeans	sklearn	fit	10000	2	random	30	3	1	0.0	NaN	0.1038	0.0440	30.0	0.0105	0.0146	30.0	9.89	3.01
27	KMeans	sklearn	fit	10000	100	random	30	3	1	0.0	NaN	0.0226	0.0271	30.0	0.0090	0.0142	30.0	2.51	1.91
36	KMeans	sklearn	fit	1000000	2	k-means++	30	3	1	0.0	NaN	0.0305	0.0269	30.0	0.0087	0.0137	30.0	3.51	1.96
45	KMeans	sklearn	fit	1000000	2	random	30	3	1	0.0	NaN	0.2784	0.0624	30.0	0.0459	0.0143	30.0	6.07	4.36
54	KMeans	sklearn	fit	1000000	100	k-means++	30	3	1	0.0	NaN	0.1417	0.0276	30.0	0.0190	0.0146	30.0	7.46	1.89
63	KMeans	sklearn	fit	1000000	100	random	30	3	1	0.0	NaN	0.1836	0.0334	30.0	0.0285	0.0149	30.0	6.44	2.24
3	KMeans	sklearn	fit	10000	2	k-means++	30	10	1	0.0	NaN	0.0055	0.0156	NaN	0.0043	0.0126	NaN	1.28	1.24
6	KMeans	sklearn	fit	10000	2	k-means++	30	300	1	0.0	NaN	0.0052	0.0148	NaN	0.0045	0.0131	NaN	1.16	1.13
12	KMeans	sklearn	fit	10000	2	random	30	10	1	0.0	NaN	0.0055	0.0156	NaN	0.0043	0.0125	NaN	1.28	1.25
15	KMeans	sklearn	fit	10000	2	random	30	300	1	0.0	NaN	0.0051	0.0145	NaN	0.0044	0.0128	NaN	1.16	1.13
21	KMeans	sklearn	fit	10000	100	k-means++	30	10	1	0.0	NaN	0.0060	0.0160	NaN	0.0048	0.0125	NaN	1.25	1.28
24	KMeans	sklearn	fit	10000	100	k-means++	30	300	1	0.0	NaN	0.0053	0.0151	NaN	0.0045	0.0131	NaN	1.18	1.15
30	KMeans	sklearn	fit	10000	100	random	30	10	1	0.0	NaN	0.0054	0.0153	NaN	0.0044	0.0126	NaN	1.23	1.21
33	KMeans	sklearn	fit	10000	100	random	30	300	1	0.0	NaN	0.0051	0.0145	NaN	0.0044	0.0128	NaN	1.16	1.13
39	KMeans	sklearn	fit	1000000	2	k-means++	30	10	1	0.0	NaN	0.0055	0.0158	NaN	0.0043	0.0125	NaN	1.28	1.26
42	KMeans	sklearn	fit	1000000	2	k-means++	30	300	1	0.0	NaN	0.0051	0.0147	NaN	0.0046	0.0133	NaN	1.11	1.11
48	KMeans	sklearn	fit	1000000	2	random	30	10	1	0.0	NaN	0.0058	0.0153	NaN	0.0048	0.0125	NaN	1.21	1.22
51	KMeans	sklearn	fit	1000000	2	random	30	300	1	0.0	NaN	0.0052	0.0148	NaN	0.0045	0.0131	NaN	1.16	1.13
57	KMeans	sklearn	fit	1000000	100	k-means++	30	10	1	0.0	NaN	0.0193	0.0563	NaN	0.0045	0.0128	NaN	4.29	4.40
60	KMeans	sklearn	fit	1000000	100	k-means++	30	300	1	0.0	NaN	0.0052	0.0148	NaN	0.0045	0.0130	NaN	1.16	1.14
66	KMeans	sklearn	fit	1000000	100	random	30	10	1	0.0	NaN	0.0056	0.0152	NaN	0.0046	0.0127	NaN	1.22	1.20
69	KMeans	sklearn	fit	1000000	100	random	30	300	1	0.0	NaN	0.0051	0.0145	NaN	0.0045	0.0129	NaN	1.13	1.12

print_results(algo="KMeans", versus_lib="daal4py", compare_cols=["n_iter"])

plot_results(algo="KMeans", versus_lib="daal4py", group_by_cols=["init", "max_iter", "n_clusters", "n_init", "tol", "function"], compare_cols=["n_iter"])